© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2019
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    康
    -0.23
    Volumes
    -0.23
    ç±³
    -0.23
    <|endoftext|>
    -0.22
    unct
    -0.21
     ment
    -0.21
    mil
    -0.21
    EMENT
    -0.21
     Bedford
    -0.21
     considered
    -0.21
    POSITIVE LOGITS
     Comple
    0.24
     edits
    0.23
    æĸ°å½¢åĬ¿
    0.23
    å¡«åĨĻ
    0.23
    缺失
    0.23
    Ĥæķ°
    0.23
    空çĻ½
    0.23
    çļĦå±ĢéĿ¢
    0.22
     Reason
    0.22
     edit
    0.22
    Activations Density 0.000%

    No Known Activations